Claude Global Agent Directives — AI skill for Claude Code
A refined global CLAUDE.md for reliable, verification-first AI agent workflows.
How to install Claude Global Agent Directives
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open BoykaHe/claude-global-agent-directives and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Global Agent Directives does
A refined global CLAUDE.md for reliable, verification-first AI agent workflows.
Alternatives in AI
- J Space Cognition Suite V3.7 — J-Space Cognition Suite V3.7 - AI cognitive-enhancement Skills based on Anthropic's J-space global workspace r 3k ★
- LongHorizon Harness — The long-horizon computer-use harness 1.3k ★
- Pilotfish — Multi-model orchestration layer for Claude Code — the frontier model plans, cheaper models execute, verificati 688 ★
README
CLAUDE.md — Global Agent Directives
A refined global `CLAUDE.md` for reliable, verification-first AI agent workflows.
What This Is
A set of universal operating rules for [Claude Code](https://code.claude.com), designed to be placed at `~/.claude/CLAUDE.md` and loaded automatically at every session start regardless of project.
These directives address known structural limitations of Claude Code — context decay, file read caps, tool result truncation, and default biases toward minimal output — with explicit safeguards and verification requirements.
Design Principles
- Conservative by default — smallest correct change, preserve existing behaviour
- Thorough mode on demand — activated only when the user explicitly requests refactoring or architecture review (or uses
[REFAC]/[REVISE]/[ARCH]tags) - Verification status ladder — every task reports its actual verification level (Planned → Drafted → Edited → Reviewed → Verified locally → Validated externally)
- Technical safeguards — phased execution (≤5 files), sub-agent swarming (>5 files), context decay awareness (>10 messages), chunked reading (>500 lines)
Install
# Option A: curl directly
curl -o ~/.claude/CLAUDE.md https://raw.githubusercontent.com/BoykaHe/claude-global-agent-directives/main/CLAUDE.md
# Option B: clone and copy
git clone https://github.com/BoykaHe/claude-global-agent-directives.git
cp claude-global-agent-directives/CLAUDE.md ~/.claude/CLAUDE.md
Claude Code reads `~/.claude/CLAUDE.md` automatically at session start.
Versioning
This file is version-controlled. Check the commit history for change log. Current version: **v3.0.0**.
Attribution
This repository contains an adapted and expanded version of a global `CLAUDE.md` for technical-sharing purposes.
Its primary inspiration and reference point is [`iamfakeguru/claude-md`](https://github.com/iamfakeguru/claude-md), whose ideas on Claude Code safeguards, context handling, and operational
Related Skills
Base Harness
A minimal, reliable, provider-agnostic AI agent harness in TypeScript — the agentic loop, tools, permissions,
Global Agent Memory
Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an
Turbo Quant Memory
Local-first MCP memory server for AI coding agents with compact retrieval and project/global scopes.
Whimsical Strategies Skill
Claude Code skill: generate out-of-distribution adversarial prompts for AI agents using Microsoft Research's w
Ajaia Delivery Ops
AI delivery operations system for a Patient Acquisition & Growth Agent engagement — built on the DOE framework
Claude Image
教 Claude Code/Codex 真正用好 gpt-image-2 的 skill 包 · Drop-in skill teaching agents to actually use GPT Image 2 — i
Related Agents
Statutory Researcher
Searches primary normative acts (statutes, regulations, directives, secondary legislation) for issues listed i
Content Creator
Invoke when the user needs any form of marketing content created or refined — blog posts, ad copy, email campa
Story Refiner
Interactive story clarification agent for the aiagent Go project. Explores the codebase to understand context,